Alternatives to Shinkai Local Ai Agents

Open-source local AI workspace for fine-tuning and running LLMs, image, and video models on your own GPU

Open-source, self-hosted AI assistant and agent framework with unified model routing, a full RAG chain, and local/remote MCP tooling.

AgenticSeek is a fully local, open-source AI assistant that browses the web, writes and runs code, and plans multi-step tasks on your own machine.

Free, open-source web UI for prototyping multi-agent AI workflows on AutoGen AgentChat — build agent teams without writing code.

ChatDev 2.0 (DevAll) is a free, open-source zero-code platform for multi-agent orchestration from YAML or JSON config.

AgentScope is an open-source Python framework from Alibaba for building distributed multi-agent AI systems.

Dify is an open-source visual builder for agentic workflows and RAG pipelines, deployable on cloud, VPC, or self-hosted Docker.

DeerFlow is an open-source SuperAgent harness that researches, codes, and creates inside a persistent Docker sandbox.

Google Antigravity runs parallel local coding agents across real codebases from $0/month.

Build, debug, and deploy AI agents with an open-source visual agent development platform you host yourself.

Open-source AI automation: describe a workflow in chat, get agents, tables, and 760+ app connections you can self-host.

Hermes Desktop is a free, open-source desktop GUI for the Hermes Agent — a self-hosted AI agent with a built-in learning loop that turns

Open-source library of 817 structured cybersecurity skill files your AI coding agent loads on demand, mapped to MITRE ATT&CK and licensed Apache 2.0.

Open-source, local-first desktop AI client that connects to multiple model providers and keeps your data on your machine.

Godcoder is a local-first, open-source AI coding agent that builds and optimizes its own harness on your desktop.

Free open-source CLI benchmark that measures local LLM tokens-per-second throughput through Ollama and posts each run to a public results

LLM routing that picks the cheapest model still hitting your quality bar, without stalling the agent loop.

Sakana AI builds Japanese-specialised LLMs and Fugu multi-model orchestration for finance, defense and intelligence teams.

Enterprise agent workforce platform for building, operating, and governing AI agents across on-prem, hybrid, and multi-cloud environments.

Lyzr's Opencontroller is an AI agent control plane to run, monitor, and govern enterprise agents built on any framework.

CrewAI is an enterprise multi-agent platform for building, governing, and observing agentic workflows in production.

Visual low-code canvas for building AI agents, RAG pipelines, and MCP servers, deployable as an API or self-hosted.

Microsoft's open-source, code-first Python framework for building stateful, data-intensive conversational AI agents.

Coworker AI routes enterprise tasks across 13 open and closed models on top of OM2 organizational memory.

Open-source browser extension that runs AI models locally via Ollama — chat, agent mode, and translations without sending data to the cloud.

AI Playground runs one prompt across up to 3 AI models side by side, with your own API keys and data kept local.

Free OpenClaw Book: a GitBook reference that takes the OpenClaw AI assistant apart, chapter by chapter, with source-traced deep dives

CodeLoom is a free, open-source local AI code assistant that weaves multiple offline LLMs into one desktop coding workspace.

Relevance AI builds enterprise AI agent workforces that run autonomously with built-in evals and governance.

StackAI is an enterprise AI agent factory for building, deploying, and governing agentic workflows.